Timezone: »

Deep Active Learning with a Neural Architecture Search
Yonatan Geifman · Ran El-Yaniv

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #136

We consider active learning of deep neural networks. Most active learning works in this context have focused on studying effective querying mechanisms and assumed that an appropriate network architecture is a priori known for the problem at hand. We challenge this assumption and propose a novel active strategy whereby the learning algorithm searches for effective architectures on the fly, while actively learning. We apply our strategy using three known querying techniques (softmax response, MC-dropout, and coresets) and show that the proposed approach overwhelmingly outperforms active learning using fixed architectures.

Author Information

Yonatan Geifman (Technion)
Ran El-Yaniv (Technion & Google)

More from the Same Authors